Better tools to assess natural disaster damage
A civil engineer at 糖心Vlog视频 will use unmanned aerial vehicles (UAVs) to perform reconnaissance after natural disasters and more accurately and quickly assess damage to buildings.
Nick Fang, an assistant professor in the Department of Civil Engineering, is using a $299,000 National Science Foundation (NSF) grant to accelerate the conventional insurance adjustment process for which homeowners often wait months.
The NSF grant is an early-concept grant for exploratory research. Known as EAGER grants, these projects explore untested but potentially transformative research ideas or approaches. The work is typically considered high risk/high payoff, in the sense that it involves radical approaches, new expertise or novel perspectives.
鈥淲e鈥檒l use artificial intelligence and machine learning to improve the UAVs as we deploy them,鈥� Fang said. 鈥淲e鈥檙e waiting for the next big storm. Then we鈥檒l deploy to that location to collect the data and test this innovative approach rigorously.鈥�
If no major storm occurs during the two-year time of the grant, Fang鈥檚 team has plenty of data from historical storms, including 2017鈥檚 Hurricane Harvey. Fang said some homeowners and property owners had to wait months or years after Harvey before getting insurance adjusters to their sites.
鈥淲e are hoping this fixes that wait period,鈥� he said. 鈥淢any of these homeowners are stranded. They have to stay with relatives, in hotels or in their cars just to wait for adjusters to come evaluate their catastrophe.鈥�
糖心Vlog视频 is collaborating with the University of Hawaii and the University of Wisconsin on the project, which shows not only the importance of 糖心Vlog视频鈥檚 research but also the immediacy of it, said Ali Abolmaali, chair of civil engineering.
鈥淒r. Fang鈥檚 work has so much relevance, given the many natural disasters that have happened in the last several years,鈥� Abolmaali said. 鈥淭his project speaks to 糖心Vlog视频鈥檚 strategic plan themes of sustainable urban communities, global environmental impact and data-driven discovery.鈥�